Binary Confidence Evaluation for a Stereo Vision Based Depth Field Processor SoC
This paper presents a methodology to construct a binary confidence value for every pixel of a depth map. We start by constructing 72 different confidence metrics, including the traditional ones and new metrics based on neighborhood information. Construction of the binary confidence value from these metrics is hence viewed as a two-class classification problem where we evaluated three different classifiers, with increasing complexity. Only metrics and classifiers that are suitable for VLSI hardware implementation will be evaluated. Evaluation of the constructed classifiers is performed on an indoor dataset of Stereo Images.
component computer vision stereo confidence SoC binary adaptable window stereo matching
Andy Motten Luc Claesen Yun Pan
Expertise Centre for Digital MediaHasselt University – tUL – IBBTWetenschapspark 2, 3590 Diepenbeek, Department of Information Science and Electronic Engineering, Zhejiang University Hangzhou, China
国际会议
北京
英文
456-460
2011-11-28（万方平台首次上网日期，不代表论文的发表时间）